Liu Hui, Mo Zi-Hua, Yang Hang, Zhang Zheng-Fu, Hong Dian, Wen Long, Lin Min-Yin, Zheng Ying-Yi, Zhang Zhi-Wei, Xu Xiao-Wei, Zhuang Jian, Wang Shu-Shui
Department of Pediatric Cardiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangdong Cardiovascular Institute, Guangzhou, China.
Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Front Pediatr. 2021 May 19;9:648255. doi: 10.3389/fped.2021.648255. eCollection 2021.
Williams-Beuren syndrome (WBS) is a rare genetic syndrome with a characteristic "elfin" facial gestalt. The "elfin" facial characteristics include a broad forehead, periorbital puffiness, flat nasal bridge, short upturned nose, wide mouth, thick lips, and pointed chin. Recently, deep convolutional neural networks (CNNs) have been successfully applied to facial recognition for diagnosing genetic syndromes. However, there is little research on WBS facial recognition using deep CNNs. The purpose of this study was to construct an automatic facial recognition model for WBS diagnosis based on deep CNNs. The study enrolled 104 WBS children, 91 cases with other genetic syndromes, and 145 healthy children. The photo dataset used only one frontal facial photo from each participant. Five face recognition frameworks for WBS were constructed by adopting the VGG-16, VGG-19, ResNet-18, ResNet-34, and MobileNet-V2 architectures, respectively. ImageNet transfer learning was used to avoid over-fitting. The classification performance of the facial recognition models was assessed by five-fold cross validation, and comparison with human experts was performed. The five face recognition frameworks for WBS were constructed. The VGG-19 model achieved the best performance. The accuracy, precision, recall, F1 score, and area under curve (AUC) of the VGG-19 model were 92.7 ± 1.3%, 94.0 ± 5.6%, 81.7 ± 3.6%, 87.2 ± 2.0%, and 89.6 ± 1.3%, respectively. The highest accuracy, precision, recall, F1 score, and AUC of human experts were 82.1, 65.9, 85.6, 74.5, and 83.0%, respectively. The AUCs of each human expert were inferior to the AUCs of the VGG-16 (88.6 ± 3.5%), VGG-19 (89.6 ± 1.3%), ResNet-18 (83.6 ± 8.2%), and ResNet-34 (86.3 ± 4.9%) models. This study highlighted the possibility of using deep CNNs for diagnosing WBS in clinical practice. The facial recognition framework based on VGG-19 could play a prominent role in WBS diagnosis. Transfer learning technology can help to construct facial recognition models of genetic syndromes with small-scale datasets.
威廉姆斯-博伦综合征（WBS）是一种罕见的遗传综合征，具有典型的“小精灵”面部特征。“小精灵”面部特征包括额头宽阔、眶周浮肿、鼻梁扁平、鼻尖上翘且短、嘴巴宽大、嘴唇厚实以及下巴尖细。最近，深度卷积神经网络（CNN）已成功应用于面部识别以诊断遗传综合征。然而，利用深度CNN进行WBS面部识别的研究较少。本研究的目的是基于深度CNN构建一个用于WBS诊断的自动面部识别模型。该研究纳入了104名WBS患儿、91例患有其他遗传综合征的患儿以及145名健康儿童。照片数据集仅使用了每位参与者的一张正面面部照片。分别采用VGG - 16、VGG - 19、ResNet - 18、ResNet - 34和MobileNet - V2架构构建了五个用于WBS的面部识别框架。使用ImageNet迁移学习来避免过拟合。通过五折交叉验证评估面部识别模型的分类性能，并与人类专家进行比较。构建了五个用于WBS的面部识别框架。VGG - 19模型表现最佳。VGG - 19模型的准确率、精确率、召回率、F1分数和曲线下面积（AUC）分别为92.7±1.3%、94.0±5.6%、81.7±3.6%、87.2±2.0%和89.6±1.3%。人类专家的最高准确率、精确率、召回率、F1分数和AUC分别为82.1、65.9、85.6、74.5和83.0%。每位人类专家的AUC均低于VGG - 16（88.6±3.5%）、VGG - 19（89.6±1.3%）、ResNet - 18（83.6±8.2%）和ResNet - 34（86.3±4.9%）模型的AUC。本研究突出了在临床实践中使用深度CNN诊断WBS的可能性。基于VGG - 19的面部识别框架在WBS诊断中可发挥重要作用。迁移学习技术有助于利用小规模数据集构建遗传综合征的面部识别模型。
